AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

A Generalized Unbiased Risk Estimator for Learning with Augmented Classes

Senlin Shu, Shuo He, Haobo Wang, Hongxin Wei, Tao Xiang, Lei Feng

AAAI 2023 · Label-efficient and robust learning › Recognition and long-tail · approach: Learning from unlabeled and positive-unlabeled data

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use generalized URE with generalized cross entropy and risk-penalty regularization instead of EULACLAC classification · MNIST, Fashion-MNIST, Kuzushiji-MNIST, SVHNaccuracy: MNIST: 0.952±0.006 -> 0.960±0.006; Fashion: 0.840±0.034 -> 0.875±0.010; Kuzushiji: 0.881±0.016 -> 0.927±0.009; SVHN: 0.8Improved
Use generalized URE with generalized cross entropy and risk-penalty regularization instead of EULACLAC classification · MNIST, Fashion-MNIST, Kuzushiji-MNIST, SVHNMacro-F1: MNIST: 0.951±0.007 -> 0.960±0.006; Fashion: 0.813±0.070 -> 0.872±0.010; Kuzushiji: 0.877±0.021 -> 0.926±0.008; SVHN: 0.8Improved
Use generalized URE with generalized cross entropy and risk-penalty regularization instead of EULACLAC classification · MNIST, Fashion-MNIST, Kuzushiji-MNIST, SVHNAUC: MNIST: 0.996±0.002 -> 0.998±0.001; Fashion: 0.953±0.039 -> 0.985±0.002; Kuzushiji: 0.981±0.009 -> 0.994±0.001; SVHN: 0.9Improved
Replace risk-penalty regularization with ReLU risk correction (ablation)NRPR · MNIST, Fashion-MNIST, Kuzushiji-MNIST, SVHNaccuracy: NRPR: 0.960±0.006 vs ReLU: 0.865±0.034; 0.870±0.009 vs 0.809±0.021; 0.927±0.009 vs 0.853±0.029; 0.865±0.010 vs 0.734±0.0Hurt
Replace risk-penalty regularization with ABS risk correction (ablation)NRPR · MNIST, Fashion-MNIST, Kuzushiji-MNIST, SVHNaccuracy: NRPR: 0.960±0.006 vs ABS: 0.776±0.014; 0.870±0.009 vs 0.747±0.019; 0.927±0.009 vs 0.757±0.027; 0.865±0.010 vs 0.695±0.00Hurt
Add risk-penalty regularization with an intermediate λ rather than setting λ=0 (ablation)NRPR · Four regular-scale datasetsaccuracy, Macro-F1, and AUCImproved
Account for known-class prior shift during training (ablation)NRPR · Usps and Optdigits with class prior shiftaccuracyImproved
Increase the number of unlabeled examples (ablation)NRPR · Four regular-scale datasetsaccuracy, Macro-F1, and AUCImproved
Vary the assumed mixture proportion (ablation)NRPR · Usps and OptdigitsaccuracyMixed

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy